Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1626 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1019. Min Act: -0.0001

Data Index: 1242181 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1614. Min Act: -0.0001

Data Index: 246508 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1074. Min Act: -0.0001

Data Index: 661134 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1178. Min Act: -0.0001

Data Index: 56425 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0284. Min Act: -0.0001

Data Index: 380609 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.1177. Min Act: -0.0001

Data Index: 650730 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0166. Min Act: -0.0001

Data Index: 801149 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9578. Min Act: -0.0001

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0370. Min Act: -0.0001

Data Index: 537827 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0863. Min Act: -0.0001

Data Index: 908410 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9938. Min Act: -0.0001

Data Index: 682902 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9969. Min Act: -0.0001

Data Index: 1300643 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0431. Min Act: -0.0001

Data Index: 315344 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0524. Min Act: -0.0001

Data Index: 266965 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9071. Min Act: -0.0001

Data Index: 1026816 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.1614. Min Range: -1.1614

Max Act: 1.0433. Min Act: -0.0001

Data Index: 803399 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9732. Min Act: -0.0001

Data Index: 149166 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9173. Min Act: -0.0001

Data Index: 303229 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.1614. Min Range: -1.1614

Max Act: 0.9109. Min Act: -0.0001

Data Index: 785685 (C4 (Web Text))

Max Activating Token Index: 501